StyleSeg V2: Towards Robust One-shot Segmentation of Brain Tissue via Optimization-free Registration Error Perception
One-shot segmentation of brain tissue requires training registration-segmentation (reg-seg) dual-model iteratively, where reg-model aims to provide pseudo masks of unlabeled images for seg-model by warping a carefully-labeled atlas. However, the imperfect reg-model induces image-mask misalignment, poisoning the seg-model subsequently. Recent StyleSeg bypasses this bottleneck by replacing the unlabeled images with their warped copies of atlas, but needs to borrow the diverse image patterns via style transformation. Here, we present StyleSeg V2, inherited from StyleSeg but granted the ability of perceiving the registration errors. The motivation is that good registration behaves in a mirrored fashion for mirrored images. Therefore, almost at no cost, StyleSeg V2 can have reg-model itself "speak out" incorrectly-aligned regions by simply mirroring (symmetrically flipping the brain) its input, and the registration errors are symmetric inconsistencies between the outputs of original and mirrored inputs. Consequently, StyleSeg V2 allows the seg-model to make use of correctly-aligned regions of unlabeled images and also enhances the fidelity of style-transformed warped atlas image by weighting the local transformation strength according to registration errors. The experimental results on three public datasets demonstrate that our proposed StyleSeg V2 outperforms other state-of-the-arts by considerable margins, and exceeds StyleSeg by increasing the average Dice by at least 2.4%.
Code (0)
등록된 구현이 없습니다.
Tasks
One-Shot SegmentationSimilar Papers 제목 키워드 기반
Segmentation Style Discovery: Application to Skin Lesion Images
Variability in medical image segmentation, arising from annotator preferences, expertise, and their choice of tools, has been well documented. While the majority of multi-annotator segmentation approaches focus on modeli…
Image SegmentationLesion SegmentationMedical Image SegmentationSegmentation+2Neural Style Transfer Improves 3D Cardiovascular MR Image Segmentation on Inconsistent Data
Three-dimensional medical image segmentation is one of the most important problems in medical image analysis and plays a key role in downstream diagnosis and treatment. Recent years, deep neural networks have made ground…
BenchmarkingEnsemble LearningHeart SegmentationImage Segmentation+5Robust One-shot Segmentation of Brain Tissues via Image-aligned Style Transformation
One-shot segmentation of brain tissues is typically a dual-model iterative learning: a registration model (reg-model) warps a carefully-labeled atlas onto unlabeled images to initialize their pseudo masks for training a …
One-Shot SegmentationSegmentationSAM vs BET: A Comparative Study for Brain Extraction and Segmentation of Magnetic Resonance Images using Deep Learning
Brain extraction is a critical preprocessing step in various neuroimaging studies, particularly enabling accurate separation of brain from non-brain tissue and segmentation of relevant within-brain tissue compartments an…
SegmentationZero Shot SegmentationDevelopment of accurate human head models for personalized electromagnetic dosimetry using deep learning
The development of personalized human head models from medical images has become an important topic in the electromagnetic dosimetry field, including the optimization of electrostimulation, safety assessments, etc. Human…
Segmentation